| Presentation | 2021-03-05 Deep Learning-based OBSS Packet Recognition in the presence of OFDM Symbol Timing Offset Muhammad Harry Bintang Pratama, Leonardo Lanante Jr., Hiroshi Ochi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Overlapping Basic Service Set can result in packet collision and decrease network efficiency. To overcome this problem, a station must confirm the channel availability through the CCA mechanism. Besides using CCA-ED to sense the power level to detect the packet’s presence, packet detection in Wi-Fi standards depends on the packet’s preamble portion through CCA-SD that will check for a valid OFDM symbol. The power level must be within the threshold, or the preamble part must not be missed for CCA to detect the signal successfully. A deep learning-based method, such as CNN, can be used to recognize packet information without the preamble part. We propose a CNN model and suitable datasets that simulate the received packet during CCA. We also explain the role of filter size and max-pooling in signal processing point of view. Our simulations show that the proposed CNN model can classify different packet format and their modulation types. It can still recognize the packet even though different OFDM symbol timing offsets occur. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | OBSSWLANOFDMmodulation detectionCNN |
| Paper # | SIS2020-55 |
| Date of Issue | 2021-02-25 (SIS) |
| Conference Information | |
| Committee | SIS |
|---|---|
| Conference Date | 2021/3/4(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Soft Computing, etc. |
| Chair | Noriaki Suetake(Yamaguchi Univ.) |
| Vice Chair | Tomoaki Kimura(Kanagawa Inst. of Tech.) / Naoto Sasaoka(Tottori Univ.) |
| Secretary | Tomoaki Kimura(Kindai Univ.) / Naoto Sasaoka(National Inst. of Tech., Ube College) |
| Assistant | Yukihiro Bandoh(NTT) / Soh Yoshida(Kansai Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Smart Info-Media Systems |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Deep Learning-based OBSS Packet Recognition in the presence of OFDM Symbol Timing Offset |
| Sub Title (in English) | |
| Keyword(1) | OBSSWLANOFDMmodulation detectionCNN |
| 1st Author's Name | Muhammad Harry Bintang Pratama |
| 1st Author's Affiliation | Kyushu Institute of Technology(Kyushu Inst. of Tech) |
| 2nd Author's Name | Leonardo Lanante Jr. |
| 2nd Author's Affiliation | Kyushu Institute of Technology(Kyushu Inst. of Tech) |
| 3rd Author's Name | Hiroshi Ochi |
| 3rd Author's Affiliation | Kyushu Institute of Technology(Kyushu Inst. of Tech) |
| Date | 2021-03-05 |
| Paper # | SIS2020-55 |
| Volume (vol) | vol.120 |
| Number (no) | SIS-415 |
| Page | pp.pp.109-113(SIS), |
| #Pages | 5 |
| Date of Issue | 2021-02-25 (SIS) |